Prediction of Soil Moisture Content from Sentinel-2 Images Using Convolutional Neural Network (CNN)
Open Access
Abstract
Agriculture is closely associated with food and water. Agriculture is the first source of food but the biggest consumer of freshwater. The population is constantly increasing. Smart agriculture is one of the means of achieving food and water security. Smart agriculture can help improve water management and increase agricultural production, thus counteracting rapid population growth requirements. Soil moisture estimation is a critical step in agricultural water management. Soil moisture measurement techniques in situ are point measurements, labor-intensive, time-consuming, tedious, and expensive. We propose, in this research, a new approach to predict soil moisture over vegetation-covered areas from Sentinel-2 images based on a convolutional neural network (CNN). CNN architecture (3) consisting of six convolutional layers, one pooling layer, and two fully connected layers has achieved the highest prediction accuracy. Three well-known criteria including coefficient of determination (), mean absolute error (MAE), and root mean square error (RMSE) are utilized to measure the accuracy of the proposed algorithm. The Red Edge 3, NIR, and SWIR 1 are the most appropriate Sentinel-2 bands for retrieving soil moisture in vegetation-covered areas. Normalized Difference Water Index (NDWI) and Normalized Difference Vegetation Index (NDVI) are the best indicators. The use of the indicator is more proper than the use of the single Sentinel-2 band as input data for the proposed CNN architecture for predicting soil moisture. However, using combinations “that consist of some number of Sentinel-2 bands” as input data for CNN architecture is better than using each indicator separately or all of them as a group. The best values of the performance metrics were achieved using the sixth combination () composed of the Red, Red Edge 1, Red Edge 2, Red Edge 3, NIR, and Red Edge 4 bands as input data to the CNN architecture (3), as well as by using the fifth combination () composed of the Red Edge 3, NIR, Red Edge 4, and SWIR 1 bands.
Keywords
Funding Information
- The Project Supported by the Key R&D Program of Zhejiang Province (2021C02036, 2018GBJ008523, 598838-EPP-1-2018-EL-EPPKA2-CBHE-JP)
- Executive Program between the Arab Republic of Egypt and P.R of China (2021C02036, 2018GBJ008523, 598838-EPP-1-2018-EL-EPPKA2-CBHE-JP)
- Eramus+ Project (2021C02036, 2018GBJ008523, 598838-EPP-1-2018-EL-EPPKA2-CBHE-JP)
This publication has 73 references indexed in Scilit:
- The Murrumbidgee soil moisture monitoring network data setWater Resources Research, 2012
- Sentinel-2: ESA's Optical High-Resolution Mission for GMES Operational ServicesRemote Sensing of Environment, 2012
- Calibration and validation of salt-resistant hyperspectral indices for estimating soil moisture in arid landJournal of Hydrology, 2011
- Evaluation of Sentinel-2 Red-Edge Bands for Empirical Estimation of Green LAI and Chlorophyll ContentSensors, 2011
- Competition for water for the food systemPhilosophical Transactions of the Royal Society B: Biological Sciences, 2010
- Monitoring the effects of land use and cover type changes on soil moisture using remote-sensing data: A case study in China's Yongding River basinCATENA, 2010
- Remote estimation of canopy chlorophyll content in cropsGeophysical Research Letters, 2005
- The MERIS terrestrial chlorophyll indexInternational Journal of Remote Sensing, 2004
- Vegetation water content mapping using Landsat data derived normalized difference water index for corn and soybeansRemote Sensing of Environment, 2004
- Designing a spectral index to estimate vegetation water content from remote sensing data: Part 1Remote Sensing of Environment, 2002